Commit
•
2396111
1
Parent(s):
74d9e0d
Upload 10 files
Browse files- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- latest +1 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- trainer_state.json +408 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.1,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 8,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"k_proj",
|
| 23 |
+
"o_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"q_proj"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM",
|
| 28 |
+
"use_rslora": false
|
| 29 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86b128fb58d548e0e48c83d29493cedb3316572fb394e9ddc93f9679a23ba3f8
|
| 3 |
+
size 13665592
|
latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step4500
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14578e19a56d66c1a00f5d342066469b06f0050c040bee162325bdb76c8ceb89
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:846218c095e179bd77a42f34f676a0bf6ec82fc510491c129313218ad8d3af67
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,408 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.1998400213304894,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 0.5563874321368991,
|
| 14 |
+
"learning_rate": 4.000000000000001e-06,
|
| 15 |
+
"loss": 1.58,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 0.4957053999852371,
|
| 21 |
+
"learning_rate": 8.000000000000001e-06,
|
| 22 |
+
"loss": 1.4463,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 0.589756030703148,
|
| 28 |
+
"learning_rate": 1.2e-05,
|
| 29 |
+
"loss": 1.3542,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"grad_norm": 0.6420302678887735,
|
| 35 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 36 |
+
"loss": 1.3331,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.13,
|
| 41 |
+
"grad_norm": 0.7649283840590947,
|
| 42 |
+
"learning_rate": 2e-05,
|
| 43 |
+
"loss": 1.3253,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13,
|
| 48 |
+
"eval_loss": 1.3249897956848145,
|
| 49 |
+
"eval_runtime": 2000.6322,
|
| 50 |
+
"eval_samples_per_second": 6.665,
|
| 51 |
+
"eval_steps_per_second": 0.833,
|
| 52 |
+
"step": 500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.16,
|
| 56 |
+
"grad_norm": 0.7507878377667085,
|
| 57 |
+
"learning_rate": 1.9714285714285718e-05,
|
| 58 |
+
"loss": 1.3221,
|
| 59 |
+
"step": 600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.19,
|
| 63 |
+
"grad_norm": 0.6176603895840452,
|
| 64 |
+
"learning_rate": 1.942857142857143e-05,
|
| 65 |
+
"loss": 1.3126,
|
| 66 |
+
"step": 700
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.21,
|
| 70 |
+
"grad_norm": 0.7327398805078954,
|
| 71 |
+
"learning_rate": 1.9142857142857146e-05,
|
| 72 |
+
"loss": 1.3055,
|
| 73 |
+
"step": 800
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.24,
|
| 77 |
+
"grad_norm": 0.6839292302496646,
|
| 78 |
+
"learning_rate": 1.885714285714286e-05,
|
| 79 |
+
"loss": 1.3093,
|
| 80 |
+
"step": 900
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.27,
|
| 84 |
+
"grad_norm": 0.607074650571682,
|
| 85 |
+
"learning_rate": 1.8571428571428575e-05,
|
| 86 |
+
"loss": 1.2985,
|
| 87 |
+
"step": 1000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.27,
|
| 91 |
+
"eval_loss": 1.2995541095733643,
|
| 92 |
+
"eval_runtime": 1951.5754,
|
| 93 |
+
"eval_samples_per_second": 6.833,
|
| 94 |
+
"eval_steps_per_second": 0.854,
|
| 95 |
+
"step": 1000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.29,
|
| 99 |
+
"grad_norm": 0.74727636749315,
|
| 100 |
+
"learning_rate": 1.8285714285714288e-05,
|
| 101 |
+
"loss": 1.3017,
|
| 102 |
+
"step": 1100
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.32,
|
| 106 |
+
"grad_norm": 0.6311499573020434,
|
| 107 |
+
"learning_rate": 1.8e-05,
|
| 108 |
+
"loss": 1.2896,
|
| 109 |
+
"step": 1200
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.35,
|
| 113 |
+
"grad_norm": 0.5915205156004358,
|
| 114 |
+
"learning_rate": 1.7714285714285717e-05,
|
| 115 |
+
"loss": 1.2834,
|
| 116 |
+
"step": 1300
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.37,
|
| 120 |
+
"grad_norm": 0.5946814358633083,
|
| 121 |
+
"learning_rate": 1.742857142857143e-05,
|
| 122 |
+
"loss": 1.3073,
|
| 123 |
+
"step": 1400
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.4,
|
| 127 |
+
"grad_norm": 0.6097257778288048,
|
| 128 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 129 |
+
"loss": 1.2843,
|
| 130 |
+
"step": 1500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.4,
|
| 134 |
+
"eval_loss": 1.2924432754516602,
|
| 135 |
+
"eval_runtime": 1987.1893,
|
| 136 |
+
"eval_samples_per_second": 6.71,
|
| 137 |
+
"eval_steps_per_second": 0.839,
|
| 138 |
+
"step": 1500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.43,
|
| 142 |
+
"grad_norm": 0.596713525589904,
|
| 143 |
+
"learning_rate": 1.6857142857142858e-05,
|
| 144 |
+
"loss": 1.2748,
|
| 145 |
+
"step": 1600
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.45,
|
| 149 |
+
"grad_norm": 0.6872784300870175,
|
| 150 |
+
"learning_rate": 1.6571428571428574e-05,
|
| 151 |
+
"loss": 1.2971,
|
| 152 |
+
"step": 1700
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.48,
|
| 156 |
+
"grad_norm": 0.5519473130229932,
|
| 157 |
+
"learning_rate": 1.6285714285714287e-05,
|
| 158 |
+
"loss": 1.2746,
|
| 159 |
+
"step": 1800
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.51,
|
| 163 |
+
"grad_norm": 0.6633345934082727,
|
| 164 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 165 |
+
"loss": 1.2906,
|
| 166 |
+
"step": 1900
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.53,
|
| 170 |
+
"grad_norm": 0.6476833370052498,
|
| 171 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 172 |
+
"loss": 1.2813,
|
| 173 |
+
"step": 2000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.53,
|
| 177 |
+
"eval_loss": 1.2873681783676147,
|
| 178 |
+
"eval_runtime": 1954.0241,
|
| 179 |
+
"eval_samples_per_second": 6.824,
|
| 180 |
+
"eval_steps_per_second": 0.853,
|
| 181 |
+
"step": 2000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.56,
|
| 185 |
+
"grad_norm": 0.6831512981144761,
|
| 186 |
+
"learning_rate": 1.542857142857143e-05,
|
| 187 |
+
"loss": 1.2973,
|
| 188 |
+
"step": 2100
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.59,
|
| 192 |
+
"grad_norm": 0.6111369458671693,
|
| 193 |
+
"learning_rate": 1.5142857142857144e-05,
|
| 194 |
+
"loss": 1.2847,
|
| 195 |
+
"step": 2200
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.61,
|
| 199 |
+
"grad_norm": 0.6468631061437224,
|
| 200 |
+
"learning_rate": 1.4857142857142858e-05,
|
| 201 |
+
"loss": 1.2754,
|
| 202 |
+
"step": 2300
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.64,
|
| 206 |
+
"grad_norm": 0.6799634395265591,
|
| 207 |
+
"learning_rate": 1.4571428571428573e-05,
|
| 208 |
+
"loss": 1.2857,
|
| 209 |
+
"step": 2400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.67,
|
| 213 |
+
"grad_norm": 0.7108542425010391,
|
| 214 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 215 |
+
"loss": 1.289,
|
| 216 |
+
"step": 2500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.67,
|
| 220 |
+
"eval_loss": 1.283585786819458,
|
| 221 |
+
"eval_runtime": 1870.2159,
|
| 222 |
+
"eval_samples_per_second": 7.13,
|
| 223 |
+
"eval_steps_per_second": 0.891,
|
| 224 |
+
"step": 2500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.69,
|
| 228 |
+
"grad_norm": 0.7253629154301096,
|
| 229 |
+
"learning_rate": 1.4e-05,
|
| 230 |
+
"loss": 1.2793,
|
| 231 |
+
"step": 2600
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.72,
|
| 235 |
+
"grad_norm": 0.614991663938332,
|
| 236 |
+
"learning_rate": 1.3714285714285716e-05,
|
| 237 |
+
"loss": 1.2767,
|
| 238 |
+
"step": 2700
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.75,
|
| 242 |
+
"grad_norm": 0.5699407855446496,
|
| 243 |
+
"learning_rate": 1.3428571428571429e-05,
|
| 244 |
+
"loss": 1.2719,
|
| 245 |
+
"step": 2800
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.77,
|
| 249 |
+
"grad_norm": 0.763568295530126,
|
| 250 |
+
"learning_rate": 1.3142857142857145e-05,
|
| 251 |
+
"loss": 1.2733,
|
| 252 |
+
"step": 2900
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.8,
|
| 256 |
+
"grad_norm": 0.6538876064837678,
|
| 257 |
+
"learning_rate": 1.2857142857142859e-05,
|
| 258 |
+
"loss": 1.2822,
|
| 259 |
+
"step": 3000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.8,
|
| 263 |
+
"eval_loss": 1.2801251411437988,
|
| 264 |
+
"eval_runtime": 1889.0286,
|
| 265 |
+
"eval_samples_per_second": 7.059,
|
| 266 |
+
"eval_steps_per_second": 0.882,
|
| 267 |
+
"step": 3000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.83,
|
| 271 |
+
"grad_norm": 0.6413250796291871,
|
| 272 |
+
"learning_rate": 1.2571428571428572e-05,
|
| 273 |
+
"loss": 1.2709,
|
| 274 |
+
"step": 3100
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.85,
|
| 278 |
+
"grad_norm": 0.7125599551490435,
|
| 279 |
+
"learning_rate": 1.2285714285714288e-05,
|
| 280 |
+
"loss": 1.2829,
|
| 281 |
+
"step": 3200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.88,
|
| 285 |
+
"grad_norm": 0.6792031678140497,
|
| 286 |
+
"learning_rate": 1.2e-05,
|
| 287 |
+
"loss": 1.2728,
|
| 288 |
+
"step": 3300
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.91,
|
| 292 |
+
"grad_norm": 0.6989586202409576,
|
| 293 |
+
"learning_rate": 1.1714285714285716e-05,
|
| 294 |
+
"loss": 1.2835,
|
| 295 |
+
"step": 3400
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.93,
|
| 299 |
+
"grad_norm": 0.7569471708203911,
|
| 300 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 301 |
+
"loss": 1.2793,
|
| 302 |
+
"step": 3500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.93,
|
| 306 |
+
"eval_loss": 1.2773550748825073,
|
| 307 |
+
"eval_runtime": 1896.8518,
|
| 308 |
+
"eval_samples_per_second": 7.03,
|
| 309 |
+
"eval_steps_per_second": 0.879,
|
| 310 |
+
"step": 3500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.96,
|
| 314 |
+
"grad_norm": 0.6242374298012554,
|
| 315 |
+
"learning_rate": 1.1142857142857143e-05,
|
| 316 |
+
"loss": 1.2805,
|
| 317 |
+
"step": 3600
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.99,
|
| 321 |
+
"grad_norm": 0.6585613373985719,
|
| 322 |
+
"learning_rate": 1.0857142857142858e-05,
|
| 323 |
+
"loss": 1.265,
|
| 324 |
+
"step": 3700
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.01,
|
| 328 |
+
"grad_norm": 0.7452400076297672,
|
| 329 |
+
"learning_rate": 1.0571428571428572e-05,
|
| 330 |
+
"loss": 1.2589,
|
| 331 |
+
"step": 3800
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.04,
|
| 335 |
+
"grad_norm": 0.7861020289489161,
|
| 336 |
+
"learning_rate": 1.0285714285714285e-05,
|
| 337 |
+
"loss": 1.2616,
|
| 338 |
+
"step": 3900
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.07,
|
| 342 |
+
"grad_norm": 0.7757094950303476,
|
| 343 |
+
"learning_rate": 1e-05,
|
| 344 |
+
"loss": 1.2721,
|
| 345 |
+
"step": 4000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.07,
|
| 349 |
+
"eval_loss": 1.2751243114471436,
|
| 350 |
+
"eval_runtime": 1895.5553,
|
| 351 |
+
"eval_samples_per_second": 7.035,
|
| 352 |
+
"eval_steps_per_second": 0.879,
|
| 353 |
+
"step": 4000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.09,
|
| 357 |
+
"grad_norm": 0.6999523427612176,
|
| 358 |
+
"learning_rate": 9.714285714285715e-06,
|
| 359 |
+
"loss": 1.2649,
|
| 360 |
+
"step": 4100
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.12,
|
| 364 |
+
"grad_norm": 0.6528269639884913,
|
| 365 |
+
"learning_rate": 9.42857142857143e-06,
|
| 366 |
+
"loss": 1.2675,
|
| 367 |
+
"step": 4200
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.15,
|
| 371 |
+
"grad_norm": 0.8019204201326198,
|
| 372 |
+
"learning_rate": 9.142857142857144e-06,
|
| 373 |
+
"loss": 1.2775,
|
| 374 |
+
"step": 4300
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.17,
|
| 378 |
+
"grad_norm": 0.8453041527524593,
|
| 379 |
+
"learning_rate": 8.857142857142858e-06,
|
| 380 |
+
"loss": 1.2682,
|
| 381 |
+
"step": 4400
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.2,
|
| 385 |
+
"grad_norm": 0.6858153075780669,
|
| 386 |
+
"learning_rate": 8.571428571428571e-06,
|
| 387 |
+
"loss": 1.2753,
|
| 388 |
+
"step": 4500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.2,
|
| 392 |
+
"eval_loss": 1.2731624841690063,
|
| 393 |
+
"eval_runtime": 2031.5498,
|
| 394 |
+
"eval_samples_per_second": 6.564,
|
| 395 |
+
"eval_steps_per_second": 0.821,
|
| 396 |
+
"step": 4500
|
| 397 |
+
}
|
| 398 |
+
],
|
| 399 |
+
"logging_steps": 100,
|
| 400 |
+
"max_steps": 7500,
|
| 401 |
+
"num_input_tokens_seen": 0,
|
| 402 |
+
"num_train_epochs": 2,
|
| 403 |
+
"save_steps": 500,
|
| 404 |
+
"total_flos": 6.185622662887244e+18,
|
| 405 |
+
"train_batch_size": 8,
|
| 406 |
+
"trial_name": null,
|
| 407 |
+
"trial_params": null
|
| 408 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79f8035953d5870f087a7a17458da2cf372db61c1c76026b9673c91746827170
|
| 3 |
+
size 6008
|